OpenAssistant Storms YouTube!
Following the release of the OpenAssistant dataset, models and chat capabilities, YouTube has been on fire (almost as much as our servers) with OpenAssistant videos.
Below are some to check out.
If you want more, here is a playlist of all the recent videos we could find.
OpenAssistant RELEASED! The world's best open-source Chat AI!
We're excited to announce the release of OpenAssistant!
The future of AI development depends heavily on high quality datasets and models being made publicly available, and that's exactly what this project does.
Our team has worked tirelessly over the past several months collecting large amounts of text-based input and feedback to create an incredibly diverse and unique dataset designed specifically for training language models or other AI applications.
With over 600k human-generated data points covering a wide range of topics and styles of writing, our dataset will be an invaluable tool for any developer looking to create state-of-the-art instruction models!
To make things even better, we are making this entire dataset free and accessible to all who wish to use it. Check it out today at our HF org: OpenAssistant
On top of that, we've trained very powerful models that you can try right now at:
Watch the announcement video:
AI Alignment Livestream (aka OpenAssistant "Just Chatting")
Livestream playing around with Open Assistant and AI alignment :)
Open Assistant First Models are here!
Hello hello! we're finally here the first models of open Assistant are out and I'm going to show you a little bit of what you can do with them!
Open Assistant Inference Backend Development (Hands-On Coding)
Open Assistant Inference Backend Development (Hands-On Coding)
Join me as I build streaming inference into the Hugging Face text generation server, going through cuda, python, rust, grpc, websockets, server-sent events, and more...
The Architecture so Far!
I thought it would make sense to document our architecture as a blog post, since it would be easily visible for everyone, and it would also be nice to look back a couple months from now and see how stuff has changed :)
A lot of work was done in the past couple of weeks to establish the needed infrastructure both for data collection and inference purposes. Thanks to everyone, and especially community members who supported us so far!
Our current plan for the architecture of the Open Assistant is as follows:
We are working on setting up the inference as shown above, and considering our options for hosting, also, we want to move our authentication from the website to the python backend.
Of course, this is by no means final, and lot of questions are still open, and that is the fun of it! If you want to join us on our journey, just give our github a look!
We Need Your Help!
We Need Your Help!
Help us collect data for OpenAssistant, the largest and most open alternative to ChatGPT.